Acrobatics at the insect scale: A durable, precise, and agile micro–aerial robot
Aerial insects are exceptionally agile and precise owing to their small size and fast
neuromotor control. They perform impressive acrobatic maneuvers when evading predators …
neuromotor control. They perform impressive acrobatic maneuvers when evading predators …
Integrating Decision-Making Into Differentiable Optimization Guided Learning for End-to-End Planning of Autonomous Vehicles
We address the decision-making capability within an end-to-end planning framework that
focuses on motion prediction, decision-making, and trajectory planning. Specifically, we …
focuses on motion prediction, decision-making, and trajectory planning. Specifically, we …
[HTML][HTML] Pseudo-Normalization via Integer Fast Inverse Square Root and Its Application to Fast Computation without Division
Vector normalization is an important process in several algorithms. It is used in classical
physical calculations, mathematical techniques, and machine learning, which has witnessed …
physical calculations, mathematical techniques, and machine learning, which has witnessed …
Toward Near-Globally Optimal Nonlinear Model Predictive Control via Diffusion Models
Achieving global optimality in nonlinear model predictive control (NMPC) is challenging due
to the non-convex nature of the underlying optimization problem. Since commonly employed …
to the non-convex nature of the underlying optimization problem. Since commonly employed …
Efficient Imitation Learning for Robust, Adaptive, Vision-based Agile Flight Under Uncertainty
A Tagliabue - 2024 - dspace.mit.edu
Existing robust model predictive control (MPC) and vision-based state estimation algorithms
for agile flight, while achieving impressive performance, still demand significant onboard …
for agile flight, while achieving impressive performance, still demand significant onboard …
Safe Learning: Reinforcement Learning for Secure Process Control
J Wang - 2024 - diva-portal.org
Reinforcement learning has been widely used in the control community and has achieved
several successful applications. The safety and robustness of control systems are essential …
several successful applications. The safety and robustness of control systems are essential …
[PDF][PDF] Actor-Critic Model Predictive Control: Differentiable Optimization meets Reinforcement Learning
A Romero, E Aljalbout, Y Song, D Scaramuzza - researchgate.net
An open research question in robotics is how to combine the benefits of model-free
reinforcement learning (RL)—known for its strong task performance and flexibility in …
reinforcement learning (RL)—known for its strong task performance and flexibility in …